Automates browser interactions for LLMs using Puppeteer and the Model Context Protocol.
Connect Steel Puppeteer to Claude, Cursor or any other MCP client and it stops being a tab you switch to. Automates browser interactions for LLMs using Puppeteer and the Model Context Protocol. The steel puppeteer mcp server is what makes that connection.
A Model Context Protocol server that provides browser automation capabilities using Puppeteer and Steel. This server enables LLMs to interact with web pages, take screenshots, and execute JavaScript in a real browser environment.
The toolset is worth reading before you wire it up, because it tells you what the integration is really for:
puppeteer_navigate — Navigate to any URL in the browserInputs — - url (string, required): URL to navigate topuppeteer_screenshot — Capture screenshots of the entire page or specific elementspuppeteer_click — Click elements on the pageInput — selector (string, required): CSS selector for element to clickpuppeteer_fill — Fill out input fieldspuppeteer_select — Select an element with SELECT tagpuppeteer_hover — Hover elements on the pagepuppeteer_evaluate — Execute JavaScript in the browser consolepuppeteer_get_content — Extract content from the current pagepuppeteer_scroll — Scroll the page to trigger lazy-loadingTools — The Tools tool exposed by this serverSetup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client. The configuration blocks on this page cover the common clients.
Configuration is passed through the environment: STEEL_LOCAL, STEEL_API_KEY, STEEL_URL. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.
This sits in the browser automation group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Steel Puppeteer's toolset — puppeteer_navigate, Inputs, puppeteer_screenshot and 11 more — is a fair guide to whether it matches your workflow. It is maintained by rdvo; worth a glance at recent repository activity before you build anything load-bearing on it.
This entry was verified against Steel Puppeteer's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
| Tool | What it does |
|---|---|
| puppeteer_navigate | Navigate to any URL in the browser |
| Inputs | - url (string, required): URL to navigate to |
| puppeteer_screenshot | Capture screenshots of the entire page or specific elements |
| puppeteer_click | Click elements on the page |
| Input | selector (string, required): CSS selector for element to click |
| puppeteer_fill | Fill out input fields |
| puppeteer_select | Select an element with SELECT tag |
| puppeteer_hover | Hover elements on the page |
| puppeteer_evaluate | Execute JavaScript in the browser console |
| puppeteer_get_content | Extract content from the current page |
| puppeteer_scroll | Scroll the page to trigger lazy-loading |
| Tools | The Tools tool exposed by this server. |
| Resources | 1. **Console Logs** (console://logs) - Browser console output in text format - Includes all console messages from the browser |
| Troubleshooting | For more detailed configuration options and advanced usage, refer to the Steel documentation and the Puppeteer API reference. |
{
"mcpServers": {
"steel-puppeteer": {
"command": "node",
"args": ["path/to/steel-puppeteer/dist/index.js"],
"env": {
"STEEL_LOCAL": "true"
}
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| STEEL_LOCAL | Configuration value read at startup. | Optional |
| STEEL_API_KEY | Credential the server authenticates with. | Yes |
| STEEL_URL | Endpoint or connection string the server talks to. | Yes |
Microsoft's official browser automation server — drive a real browser through the accessibility tree, no screenshots needed.
Industrial-strength web extraction — render, scrape, crawl and search entire sites into clean markdown.
The original Chromium automation reference server — simple, screenshot-driven browser control.
Give your coding agent the full DevTools toolbox: traces, network, console, heap snapshots and Lighthouse.
Puppeteer-powered browser control that drives pages from the accessibility tree instead of pixels.
Cloud browsers for AI agents — automation sessions that run in Browserbase's fleet, not on your machine.